Abstract
An improved self-organizing map (SOM), parameterless-growing-SOM (PL-G-SOM), is proposed in this paper. To overcome problems existed in traditional SOM (Kohonen, 1982), kinds of structure-growing-SOMs or parameter-adjusting-SOMs have been invented and usually separately. Here, we combine the idea of growing SOMs (Bauer and Villmann, 1997; Dittenbach et al. 2000) and a parameterless SOM (Berglund and Sitte, 2006) together to be a novel SOM named PL-G-SOM to realize additional learning, optimal neighborhood preservation, and automatic tuning of parameters. The improved SOM is applied to construct a voice instruction learning system for partner robots adopting a simple reinforcement learning algorithm. User's instructions of voices are classified by the PL-G-SOM at first, then robots choose an expected action according to a stochastic policy. The policy is adjusted by the reward/punishment given by the user of the robot. A feeling map is also designed to express learning degrees of voice instructions. Learning and additional learning experiments used instructions in multiple languages including Japanese, English, Chinese, and Malaysian confirmed the effectiveness of our proposed system.
Highlights
Kohonen’s self-organizing map (SOM) is a kind of a neural network which maps a high-dimensional input onto a regular low-dimensional grid orderly by unsupervised learning schemes [1,2,3,4]
We propose a new voice instruction learning system using PL-GSOM given in Section 2 instead of transient SOM (T-SOM)
PL-G-SOM showed faster and better convergence than TSOM when the Euclidean distance (SE: squared error) between input and BMUs (Figure 5). This means that the classification to the input pattern was executed more efficiently by PL-G-SOM
Summary
Kohonen’s self-organizing map (SOM) is a kind of a neural network which maps a high-dimensional input onto a regular low-dimensional grid orderly by unsupervised learning schemes [1,2,3,4]. The basic idea of these kinds of SOM is to set the output feature map with a small size initially, for example, 2 units, insert rows/columns into the map in training, where/when a most visited BMU exists [7, 10] or the deviation of the distance between the units on input layer and output map [8, 9]. We combine the idea of growing SOM algorithm and the method of PLSOM to construct a novel SOM names parameterless-growing-SOM (PL-G-SOM) to tackle both problems of SOM described above This new PLG-SOM increases its structure adapting to the input data, and anneals parameters to realize sensitive clustering on the output space automatically.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
